Dipl.-Ing. Dimitrios Ernst Tsokaktsidis

Guest Scientist

Machine Learning and NVH-transfer in the automotive sector

Vehicle development processes are increasingly digitalized in order to satisfy growing market needs and economic factors. Depending on the frequency range of interest, different simulation methods (the Multibody Simulation, the Finite Element Method, the Boundary Element Method and the Statistical Energy Analysis) have been established within the NVH-departments. The spectral limitations, the manual system modelling, the accuracy of the calculation results and the calculation duration offer opportunities for improvement. The possible application of machine learning in the described context is investigated.

Research Topics

  • Supervised learning
  • Unsupervised learning
  • Transfer path analysis

Project Partners

  • Technical University of Munich
  • Daimler AG